CN112907484B - Remote sensing image color cloning method based on artificial immune algorithm - Google Patents
Remote sensing image color cloning method based on artificial immune algorithm Download PDFInfo
- Publication number
- CN112907484B CN112907484B CN202110292869.8A CN202110292869A CN112907484B CN 112907484 B CN112907484 B CN 112907484B CN 202110292869 A CN202110292869 A CN 202110292869A CN 112907484 B CN112907484 B CN 112907484B
- Authority
- CN
- China
- Prior art keywords
- antibody
- antibody population
- value
- pixel
- population
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Genetics & Genomics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Physiology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a remote sensing image color cloning method based on an artificial immune algorithm, which comprises the following steps: s1, antigen recognition Ag; s2, generating an initial antibody population, and clustering the antibody population to form a clustered antibody population G; s3, searching the antibody population class with the highest corresponding membership degree through the membership degree matrix D, and carrying out affinity calculation in the antibody elements of the class; s4, immune selection, judging whether the corresponding antibody exists in the antibody population according to the value of the affinity, if so, cloning operation is carried out, and the R, G, B value of the corresponding antibody is copied to the pixel i. If not, performing mutation operation, and updating antibody population. The invention establishes an initial antibody population on the basis of the color matching relationship of the reference image and the target image in an overlapping area, and realizes the continuous evolution of the antibody population by affinity calculation and optimization variation operation in other areas of the target image, thereby realizing the cloning and the copying of color information.
Description
Technical Field
The invention belongs to the technical field of remote sensing image processing, and particularly relates to a remote sensing image color cloning method based on an artificial immune algorithm.
Background
With the explosion development of aerospace technology, remote sensing images have become important data sources in many industries. In the actual production and application process of remote sensing image products, a large target area can relate to multi-scene images. Due to different factors such as different image acquisition times, sensor types, environmental objects and processing modes, color differences generally exist between adjacent images. The presence of such color differences can affect image interpretation accuracy and image drawing product quality. In order to eliminate the color difference between adjacent images and obtain a spliced image with a large range of uniform color tone, moderate contrast and coordinated gray level, the remote sensing image needs to be subjected to color-mixing splicing treatment.
The traditional image color matching is mainly manually solved by means of related image processing software, and due to the fact that subjectivity of image color processing is high, when a plurality of images are spliced, the whole processing effect is difficult to grasp. In recent years, with the gradual improvement of the spatial resolution and the acquisition efficiency of remote sensing images, the image data volume shows geometric growth, an automatic and intelligent remote sensing image toning method is developed, and a remote sensing image product with reliable quality is rapidly acquired, so that the problem which needs to be solved urgently is solved.
At present, a great deal of research work has been carried out in the field of remote sensing image color matching technology in the industry, including histogram matching-based methods, MASK and HIS model-based methods, Wallis filter-based methods, feature ground object color matching-based methods, color migration methods based on different color space processing, and the like, and these methods provide a technical idea for image color matching, and some methods are adopted by commercial software. However, some of these methods may have unnatural color transition when processing images of different time phases and different sensors, and some methods may require much manual intervention to achieve the desired effect. Therefore, there is a need for searching, improving and enhancing the automation and intelligence of image color matching.
The application provides a remote sensing image color cloning method based on an artificial Immune algorithm, an artificial Immune system AIS (Artificial Immune System) is an artificial intelligent method for simulating the function of a natural Immune system, and the method provides evolutionary learning mechanisms such as noise tolerance, self-learning, self-organization, memory and the like through a learning technology for realizing the natural defense mechanism of external substances, and combines the advantages of systems such as a classifier, a neural network, machine reasoning and the like. Currently, AIS has been successfully applied in the fields of fault diagnosis, pattern recognition, data mining, and the like. The technical scheme of the application aims to use the thought of an artificial immune system for reference and develop the design of the automatic color matching method between adjacent images.
Disclosure of Invention
In view of the above, in order to overcome the defects of the prior art, the present invention aims to provide a remote sensing image color cloning method based on an artificial immune algorithm.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
the remote sensing image color cloning method based on the artificial immune algorithm comprises the following steps:
s1, antigen recognition Ag; IMG based on the target image t And reference image IMG r In the overlapping region IMG tr Constructing corresponding relation of the inner R, G, B three-channel spectral values;
s2, generating an initial antibody population, and clustering the antibody population to form a clustered antibody population G;
s3, taking a pixel i of the target image except the overlapping area, calculating a membership matrix D of the pixel i and a V-class antibody center element of a clustered antibody population G, searching an antibody population class with the highest corresponding membership through the membership matrix D, and performing affinity calculation in the class antibody element;
s4, immune selection, judging whether the corresponding antibody exists in the antibody population according to the value of the affinity, if so, carrying out cloning operation, and copying the R, G, B value of the corresponding antibody to the pixel i;
if the corresponding antibody does not exist, designing a mutation operator, executing mutation operation, generating a new antibody population, and updating the antibody population;
s5, repeating the steps S2-S4 for the (i + 1) th pixel according to the new antibody population, and finishing the traversal of the target image and outputting the result image.
Further, in step S1, a specific formula for constructing the corresponding relationship is as follows:
in the formula,
and
the normalized values of the corresponding brightness values of the target image and the reference image at the same pixel point of the R, G, B channel are respectively, and C is the corresponding category of the antigen in the classification.
Further, in step S2, the method for generating the initial antibody population is as follows:
s201, calculating and acquiring an overlapping area IMG of the target image and the reference image tr ；
S202, searching the R wave band R of the target image in the overlapping area to be l (l belongs to [0,255,255 ]]) The position index array Loc is established m M is the number of all R ═ l pixels;
s203, traversing G wave band and G (Loc) of B wave band of the target image m ) And B (Loc) m ) Establishing a repeated value screening array A by using the gray value;
and S204, filtering the repeated elements in the array A, and searching the gray value of the reference image corresponding to the reserved elements according to the positions to obtain an initial antibody population S.
Further, in step S203, the formula for creating the repeated value screening array a is as follows:
the execution formula of step S204 is as follows:
in the formula, N is the number of antibodies in the overlapping region sorted according to the row number and the column number, and S is the initial antibody population type.
Further, in step S2, a specific method for clustering antibody populations is as follows:
dividing the elements in the antibody population S into V classes according to the similarity of R, G, B gray values by adopting a K-Means clustering algorithm, and recording the RGB mean value of each class as a central element Mid of each class of the clustered antibody population v Forming a cluster antibody population G, wherein the specific formula is as follows:
further, in step S3, the calculation formula of the membership matrix D is as follows:
wherein D p Is the p-th element in the membership matrix, C Rp 、C Gp 、C Bp Is the R, G, B value for the p-th central element.
Is the R, G, B value for pel i.
Further, in the step S3, the affinity Aff i The calculation formula of (a) is as follows:
in the formula, f (x) i ) The distance between the pixel i and the antibody is the minimum value of the distance between the pixel i and all individual pixels in the most similar clustered antibody population category; wherein,
in the formula, K is the number of antibodies in the class of the most similar clustered antibody population.
Further, in the step S4, if the affinity Aff is satisfied i A value of 1 indicates that the corresponding antibody is present in the antibody population;
if the affinity Aff is i A value of less than 1 indicates that the corresponding antibody is not present in the antibody population;
the formula for updating the antibody population is as follows:
M＝S+C *
wherein, C * To generate a new antibody population according to the mutation operator, S is the initial antibody population class.
Compared with the prior art, the remote sensing image color cloning method based on the artificial immune algorithm has the following advantages:
the remote sensing image color cloning method based on the artificial immune algorithm establishes an initial antibody population on the basis of the color matching relationship between a reference image and a target image in an overlapping area, realizes the continuous evolution of the antibody population through affinity calculation and optimization variation operation in other areas of the target image, further realizes the cloning and the copying of color information, can realize the automatic and accurate adjustment processing of colors between adjacent images with the overlapping area, and effectively overcomes the defects in the prior art.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and, together with the description, serve to explain the invention without limitation. In the drawings:
FIG. 1 is a flow chart of a remote sensing image color cloning method based on an artificial immune algorithm according to the embodiment of the invention;
fig. 2 is a schematic diagram of population clustering according to an embodiment of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used only for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention. Furthermore, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first," "second," etc. may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art through specific situations.
The invention will be described in detail with reference to the following embodiments with reference to the attached drawings.
The remote sensing image color cloning method based on the artificial immune algorithm gradually achieves the process with the highest antibody affinity through a series of processes such as antigen recognition, antibody proliferation, differentiation, selection, variation and the like based on the artificial immune algorithm. If the artificial immune algorithm is corresponding to a specific optimization problem to be solved, the antigen can be regarded as an objective function and a constraint condition of an actual problem to be solved, the antibody is a candidate feasible solution of the problem to be solved, the affinity between the antigen and the antibody can be regarded as the matching degree between the feasible solution and the objective function, and the affinity between the antibodies represents the similarity of the feasible solutions. The artificial immune algorithm mainly comprises the following modules:
(1) antigen recognition and initial antibody production: designing a proper antibody coding rule according to the characteristics of the problem to be optimized, and generating an initial antibody population by using prior knowledge of the problem under the coding rule;
(2) evaluation of antibody: evaluating the quality of the antibody, wherein the evaluation criteria mainly comprise the affinity and the individual concentration of the antibody, and the evaluated high-quality antibody is subjected to evolution operation and the low-quality antibody is updated;
(3) cloning and selecting: operators such as immune selection, cloning, mutation, clone inhibition, population refreshing and the like are utilized to simulate various immune operations in biological immune response, evolution rules and methods based on the clonal selection principle of a biological immune system are formed, and optimization search of various optimization problems is realized.
As shown in FIG. 1, the remote sensing image color cloning method based on the artificial immune algorithm comprises the following specific steps:
step 1: the antigen recognizes Ag. IMG based on the target image t And reference image IMG r In the overlapping region IMG tr And (4) constructing corresponding relations by using the three-channel spectrum values of the inner R, G, B. The concrete form is as follows:
in the formula,
and
the normalized values of the corresponding brightness values of the target image and the reference image at the same pixel point of the R, G, B channel are respectively, and C is the corresponding category of the antigen in the classification.
Step 2: an initial population of antibodies is generated.
2-1: calculating and acquiring an overlapping region IMG of the target image and the reference image tr ；
2-2: searching the R wave band R of the target image in the overlapping area as l (l belongs to [0,255,255 [)]) The position index array Loc is established m M is the number of all R ═ l pixels;
2-3: traversing G wave band and G (Loc) of B wave band of target image m ) And B (Loc) m ) Establishing a repeated value screening array A according to the following formula by using the gray value;
and 2-4, filtering the repeated elements in the array A, and searching the gray value of the reference image corresponding to the reserved elements according to the positions to obtain an initial antibody population S.
In the formula, N is the number of antibodies in the overlapping region sorted according to the row number and the column number, and S is the initial antibody population type.
2-5: antibody population clustering. Dividing the elements in the antibody population S into V classes according to the similarity of R, G, B gray values by adopting a K-Means clustering algorithm, and recording the RGB mean value of each class as a central element Mid of each class of the clustered antibody population v Forming a clustered antibody population G, as shown in fig. 2.
And step 3: and (5) calculating the affinity.
3-1: taking the target image except the overlapped region (the remaining group S) r ) And (4) calculating a membership matrix D of the pixel and the V-type antibody central elements of the clustered antibody population G.
Wherein D p Is the p-th element in the membership matrix, C Rp 、C Gp 、C Bp Is the R, G, B value for the p-th central element.
And (4) finding the corresponding antibody population class with the highest membership degree through the membership degree matrix, and performing affinity calculation in the antibody elements of the class, wherein the value is R, G, B of the pixel i.
3-2, calculating the affinity Aff of the pixel and all antibodies in the closest class i 。
In the formula, f (x) i ) And the distance between the pixel i and the antibody is the minimum value of the distance between the pixel i and all individual pixels in the most similar clustered antibody population category.
In the formula, K is the number of antibodies in the class of the most similar clustered antibody population.
And 4, step 4: and (4) immune selection.
4-1：Aff i If the value of (b) is 1, the pixel i has a corresponding antibody in the existing antibody population, and the cloning operation is carried out to clone the R, of the corresponding antibody,G. The B value is copied to pel i.
4-2：Aff i If the value of (d) is less than 1, the pixel i cannot find the corresponding antibody in the existing antibody population, mutation operation needs to be performed, and a real number code is adopted to perform mutation operator design, specifically as follows:
in the formula,
a band value of a target image pixel to be mutated,
is the affinity Aff in the reference image i The nearest wave band value of the minimum pixel to be mutated,
as affinity Aff in the target image i Minimum nearest neighbor band value, δ r For statistical reference image range, delta t The range of the statistical target image value range.
And 5: the antibody population is renewed. Generating new antibody population C according to mutation operator * The antibody population is updated.
M＝S+C *
Where M is the updated antibody population and S is the initial antibody population class.
Step 6: and (5) repeating the steps 2 to 5 for the (i + 1) th pixel according to the new antibody population M, and finishing the traversal of the target image and outputting a result image.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. The remote sensing image color cloning method based on the artificial immune algorithm is characterized by comprising the following steps of:
s1, antigen recognition Ag; IMG based on the target image t And reference image IMG r In the overlapping region IMG tr Constructing corresponding relation of the inner R, G, B three-channel spectral values;
s2, generating an initial antibody population, and clustering the antibody population to form a clustered antibody population G;
s3, taking a pixel i of the target image except the overlapping area, calculating a membership matrix D of the pixel i and a V-class antibody center element of a clustered antibody population G, searching an antibody population class with the highest corresponding membership through the membership matrix D, and performing affinity calculation in the class antibody element;
s4, immune selection, judging whether the corresponding antibody exists in the antibody population according to the value of the affinity, if so, carrying out cloning operation, and copying the R, G, B value of the corresponding antibody to the pixel i;
if no corresponding antibody exists, designing a mutation operator, executing mutation operation, generating a new antibody population, and updating the antibody population;
and S5, repeating the steps S2-S4 for the (i + 1) th pixel according to the updated antibody population, and finishing the traversal of the target image and outputting a result image.
2. The remote sensing image color cloning method based on artificial immune algorithm as claimed in claim 1, wherein in step S1, the concrete formula for constructing the corresponding relationship is as follows:
in the formula,
and
are respectively asThe target image and the reference image correspond to the normalized value of the brightness value at the same pixel point of the R, G, B channel, and C is the corresponding category of the antigen in the classification.
3. The remote sensing image color cloning method based on the artificial immune algorithm as claimed in claim 1, wherein in step S2, the method for generating the initial antibody population is as follows:
s201, calculating and acquiring an overlapping area IMG of the target image and the reference image tr ；
S202, searching a target image R wave band R-L in an overlapping area (L belongs to [0,255 ])]) The position index array Loc is established m M is the number of all R ═ L pixels;
s203, traversing G wave band and G (Loc) of B wave band of the target image m ) And B (Loc) m ) Establishing a repeated value screening array A by using the gray value;
and S204, filtering the repeated elements in the array A, and searching the gray value of the reference image corresponding to the reserved elements according to the positions to obtain an initial antibody population S.
4. The remote sensing image color cloning method based on artificial immune algorithm as claimed in claim 3, characterized in that: in step S203, the formula for creating the repeated value screening array a is as follows:
the execution formula of step S204 is as follows:
wherein N is the number of antibodies in the overlapping region sorted by row and column number, S is the initial antibody population class,
the R, G, B values for the pixels in the target image,
is the R, G, B value for the pixel in the reference image.
5. The remote sensing image color cloning method based on the artificial immune algorithm as claimed in claim 1, wherein: in step S2, the specific method for clustering antibody populations is as follows:
dividing the elements in the antibody population S into V classes according to the similarity of R, G, B gray values by adopting a K-Means clustering algorithm, and recording the RGB mean value of each class as a central element Mid of each class of the clustered antibody population v Forming a cluster antibody population G, wherein the specific formula is as follows:
V∈[1,N](ii) a Wherein,
the R, G, B values for the pixels in the target image,
is the R, G, B value for the pixel in the reference image.
6. The remote sensing image color cloning method based on the artificial immune algorithm as claimed in claim 1, wherein: in step S3, the calculation formula of the membership matrix D is as follows:
wherein D p Is the p-th element in the membership matrix, C Rp 、C Gp 、C Bp R, G, B value for the p-th central element;
is R, G, B for pixel i in the reference image.
7. The remote sensing image color cloning method based on artificial immune algorithm as claimed in claim 1, wherein in step S3, affinity Aff i The calculation formula of (a) is as follows:
in the formula, f (x) i ) The distance between the pixel i and the antibody is the minimum value of the distance between the pixel i and all individual pixels in the most similar clustered antibody population category; wherein,
in the formula, K is the number of antibodies in the class of the most similar clustered antibody population,
the R, G, B values for the pixels in the target image,
is the R, G, B value for the pixel in the reference image.
8. The remote sensing image color cloning method based on artificial immune algorithm as claimed in claim 7, characterized in that: in the step S4, if the affinity Aff is satisfied i A value of 1 indicates that the corresponding antibody is present in the antibody population;
if the affinity Aff is i A value of less than 1 indicates that the corresponding antibody is not present in the antibody population;
the formula for updating the antibody population is as follows:
M＝S+C *
wherein M is a renewed antibody population, C * S is the initial antibody population class for the new antibody population generated from the mutation operator.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110292869.8A CN112907484B (en) | 2021-03-18 | 2021-03-18 | Remote sensing image color cloning method based on artificial immune algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110292869.8A CN112907484B (en) | 2021-03-18 | 2021-03-18 | Remote sensing image color cloning method based on artificial immune algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112907484A CN112907484A (en) | 2021-06-04 |
| CN112907484B true CN112907484B (en) | 2022-08-12 |
Family
ID=76105548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110292869.8A Expired - Fee Related CN112907484B (en) | 2021-03-18 | 2021-03-18 | Remote sensing image color cloning method based on artificial immune algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112907484B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1873661A (en) * | 2006-06-29 | 2006-12-06 | 武汉大学 | Not supervised classification process of artificial immunity in remote sensing images |
| CN101699515A (en) * | 2009-10-30 | 2010-04-28 | 西安电子科技大学 | Multi-elite immune quantum clustering-based medical image segmenting system and multi-elite immune quantum clustering-based medical image segmenting method |
| CN101866483A (en) * | 2010-05-31 | 2010-10-20 | 西安电子科技大学 | Texture Image Segmentation Method Based on Lamarck Multi-Object Immune Algorithm |
| CN101908213A (en) * | 2010-07-16 | 2010-12-08 | 西安电子科技大学 | SAR image change detection method based on quantum immune cloning |
| CN104794732A (en) * | 2015-05-12 | 2015-07-22 | 西安电子科技大学 | Artificial immune network clustering based grayscale image segmentation method |
| CN105654498A (en) * | 2016-01-27 | 2016-06-08 | 西安电子科技大学 | Image segmentation method based on dynamic local search and immune clone automatic clustering |
| CN107516133A (en) * | 2017-03-27 | 2017-12-26 | 九次方大数据信息集团有限公司 | A kind of mixing attributive character large data sets clustering algorithm based on CSA |
| CN108595499A (en) * | 2018-03-18 | 2018-09-28 | 西安财经学院 | A kind of population cluster High dimensional data analysis method of clone's optimization |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8010296B2 (en) * | 2002-12-19 | 2011-08-30 | Drexel University | Apparatus and method for removing non-discriminatory indices of an indexed dataset |
-
2021
- 2021-03-18 CN CN202110292869.8A patent/CN112907484B/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1873661A (en) * | 2006-06-29 | 2006-12-06 | 武汉大学 | Not supervised classification process of artificial immunity in remote sensing images |
| CN101699515A (en) * | 2009-10-30 | 2010-04-28 | 西安电子科技大学 | Multi-elite immune quantum clustering-based medical image segmenting system and multi-elite immune quantum clustering-based medical image segmenting method |
| CN101866483A (en) * | 2010-05-31 | 2010-10-20 | 西安电子科技大学 | Texture Image Segmentation Method Based on Lamarck Multi-Object Immune Algorithm |
| CN101908213A (en) * | 2010-07-16 | 2010-12-08 | 西安电子科技大学 | SAR image change detection method based on quantum immune cloning |
| CN104794732A (en) * | 2015-05-12 | 2015-07-22 | 西安电子科技大学 | Artificial immune network clustering based grayscale image segmentation method |
| CN105654498A (en) * | 2016-01-27 | 2016-06-08 | 西安电子科技大学 | Image segmentation method based on dynamic local search and immune clone automatic clustering |
| CN107516133A (en) * | 2017-03-27 | 2017-12-26 | 九次方大数据信息集团有限公司 | A kind of mixing attributive character large data sets clustering algorithm based on CSA |
| CN108595499A (en) * | 2018-03-18 | 2018-09-28 | 西安财经学院 | A kind of population cluster High dimensional data analysis method of clone's optimization |
Non-Patent Citations (4)
| Title |
|---|
| Polarimetric synthetic aperture radar image unsupervised classification method based on artificial immune system;Yu Jie 等;《Journal of Applied Remote Sensing》;20140213;第1-15页 * |
| 一种人工免疫算法优化的高有效性模糊聚类图像分割;刘云龙 等;《控制与决策》;20101130;第1-5页 * |
| 基于人工免疫系统的克隆－Ｋ均值算法;詹海亮 等;《计算机仿真》;20081130;第1-4页 * |
| 基于人工免疫系统的遥感图像分类;钟燕飞 等;《遥感学报》;20050731;第1-7页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112907484A (en) | 2021-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Elngar et al. | Image classification based on CNN: a survey | |
| CN110321923B (en) | Target detection method, system and medium for fusion of feature layers of different scales of receptive fields | |
| CN109740560B (en) | Automatic human body cell protein identification method and system based on convolutional neural network | |
| JP2022551683A (en) | Methods and systems for non-invasive genetic testing using artificial intelligence (AI) models | |
| CN109344891A (en) | A classification method of hyperspectral remote sensing data based on deep neural network | |
| CN107169535A (en) | The deep learning sorting technique and device of biological multispectral image | |
| CN112464983A (en) | Small sample learning method for apple tree leaf disease image classification | |
| CN110287798B (en) | Vector network pedestrian detection method based on feature modularization and context fusion | |
| CN116704273A (en) | Self-adaptive infrared and visible light dual-mode fusion detection method | |
| KR20210127069A (en) | Method of controlling performance of fusion model neural network | |
| JP7225731B2 (en) | Imaging multivariable data sequences | |
| CN109344898A (en) | A Convolutional Neural Network Image Classification Method Based on Sparse Coding Pre-training | |
| CN115761240B (en) | Image semantic segmentation method and device for chaotic back propagation graph neural network | |
| CN112884675B (en) | Batch remote sensing image color matching engineering realization method | |
| CN112749675A (en) | Potato disease identification method based on convolutional neural network | |
| CN113191361A (en) | Shape recognition method | |
| CN112419278B (en) | Solid wood floor classification method based on deep learning | |
| CN114863266A (en) | Land use classification method based on deep space-time mode interactive network | |
| CN111161244A (en) | Surface defect detection method of industrial products based on FCN+FC-WXGBoost | |
| CN116168311B (en) | Unmanned aerial vehicle remote sensing monitoring system and method for forest diseases and insect pests | |
| CN105512686A (en) | Integrated feature selection method and system | |
| CN112907484B (en) | Remote sensing image color cloning method based on artificial immune algorithm | |
| WO2021173715A1 (en) | Methods and systems to train neural networks | |
| CN112396620A (en) | Image semantic segmentation method and system based on multiple thresholds | |
| CN114972849B (en) | Glioma type identification method, model training method, device, and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220812 |